Barelang FC

← Back to teams list

Team website
Qualification video
Team short paper
Hardware specifications

Software description

Global description file


Please give a brief summary of your walking algorithm (max. 1000 characters).

In the walking system algorithm, we adapted from the Darwin team. We use the kinematic system algorithm from RoboCup Released code Upennalizers in 2012. The part that must be modified is in walk parameters and kick parameters, this modification makes the robot work optimally. And by making a few additions to the sending and receiving of data using socket programming.


Please give a brief summary of your vision algorithm, i.e. how your robots detect balls, field borders, field lines, goalposts and other robots (max. 1000 characters).

In the vision system, we developed by using deep learning as YOLO v3 generated in Jetson TX2. Barelang-FC already implemented the YOLO for vision system, YOLO system is tended to unify the separate components of object detection becomes a single neural network. It makes bounding box of entire image feature should be considered. we use deep learning as YOLO v3 to recognize the ball, goalposts and opponent robots. In general our vision system works in a certain way, first, WebCam gets images of environmental data around the robot. The image will be processed by the CNN algorithm. The resulting CNN can reliably differentiate between categories, provide bounding boxes and class probabilities. And the coordinate of objects that are detected based on their class, such as ball, goalpost, and robot.


Please give a brief summary of how your robots localize themselves on the field (max. 1000 characters).

Localization system uses vision data and Odometry data. In our vision data system, we calculate the distance of the ball and goalposts. The distance is calculated using the angle of the head (camera) and the vertical position of the object in the image (from the camera) and the height of the camera from the ground. Whereas in the Odometry data system we use angular data of each servo at the robot leg and IMU data as the robot heading, the data is to estimate the distance of the robot's movement from its initial position. Our localization module uses 300 particles scattered in the field.


Please give a brief summary of your behavioral architecture and the decision processes of your robots (max. 1000 characters).

Our robot can play as a goalkeeper, attacking or defender player. The goalkeeper robot stays on the goal when the ball is far away when the ball approaches the keeper area the goalkeeper robot will prepare to make a save. Attacking the robot will walk towards the ball and kick the ball towards the opponent's goal. For the defending robot will defend in front of the goalkeeper's robot and help the attacking robot. To carry out their respective tasks, each robot coordinates with each other in a team through the UDP communication protocol


List your previous participation (including rank) and contribution to the RoboCup community (release of open-source software, datasets, tools etc.)

2017 (Nagoya, Japan) : The team's first participation in the RoboCup competition. in this competition, we managed to get 4th place. 2018 (Montreal, Canada) : this year was the participation of the two Barelang FC teams in the RoboCup competition and with better performance, we achieved 3rd place. 2019 (Sydney, Australia): This is the third time we have participated in a RoboCup competition. With various problems that arise in our robot, we managed to reach the quarter-finals in the main competition. The following are papers related to RoboCup that have been published by the team: 1. The deep learning development for real-time ball and goal detection of barelang-FC ( 2. Introduction to Modest Object Detection Method of Barelang-FC Soccer Robot ( 3. The deep learning development for real-time ball and goal detection of barelang-FC (


Please list RoboCup-related papers your team published in 2019.

The Paper already presented to "2019 International Conference on Applied Engineering (ICAE), Batam, 2019, presented on 2nd -3rd October 2019" and waiting for publishing into IEEE website: 1. A Control Strategy to Estimate the Robot Position Of Barelang-FC Striker